Senior AI Platform and Agentic Infrastructure Engineer
You operate and migrate an AI-native internal-audit platform to a resilient AWS or GCP production environment. You build the agent runtime, model-routing and evaluation harnesses, governed data infrastructure, security controls, and cloud foundation. You ensure production systems have high availability, disaster recovery, observability, audit logging, infrastructure as code, and controlled delivery pipelines.
Responsibilities
- Operate and migrate the prototype estate to the target platform
- Re-architect Hive Mind on AWS or GCP
- Build the agentic runtime and evaluation harness
- Implement multi-model routing and tool integrations
- Build responsible-AI and model-governance controls
- Build data infrastructure with provenance and lineage
- Engineer data protection and retention controls
- Stand up continuous-monitoring data infrastructure
- Own infrastructure as code, CI/CD, identity, networking, observability, and cost controls
Requirements
- 7+ years building and operating resilient backend or platform systems in production
- Brownfield migration experience
- Python
- SQL
- Data modeling
- TypeScript or Node
- Go
- Agent orchestration
- Model routing
- Evaluation harnesses
- MCP servers
- Responsible AI controls
- Data provenance
- Data lineage
- Encryption
- Identity and access management
- Secrets management
- AWS or GCP
- Terraform
- CI/CD
- High availability
- Disaster recovery
- Service-level objectives
- Observability
- Automated testing
- Documentation
Benefits
- Education subsidy
- Team building programs
- Company events
- Wellness allowances
- Meal allowances
- Comprehensive healthcare schemes for employees and dependants